The required libraries are loaded - MageR written by Geremy Clair (2022) is used to extract the search results from PNNL internal Data Management System (DMS) - RomicsProcessor written by Geremy Clair (2022) is used to perform trackable transformation and statistics to the dataset - proteinminion written by Geremy Clair (2022) is used to extract fasta information and to perform gene ontology, KEGG, and reactome pathways enrichement analysis (2022)
library("MageR")
library("RomicsProcessor")
library("proteinminion")
library("DT")
Using the package ‘Protein Mini-on’ (Geremy Clair 2022, in prep.), The fasta file was downloaded from Unipro for murine proteome December 30th, 2022
if(!file.exists("03_output_files/Uniprot_Mus_musculus_proteome_UP000000589_2023_01_09.fasta")){
download_UniProtFasta(proteomeID = "UP000000589",reviewed = T,export = TRUE, file="./03_output_files/Uniprot_Mus_musculus_proteome_UP000000589_2023_01_09.fasta")
}
UniProtFasta_info<-UniprotFastaParser(file = "03_output_files/Uniprot_Mus_musculus_proteome_UP000000589_2023_01_09.fasta")
## [1] "03_output_files/Uniprot_Mus_musculus_proteome_UP000000589_2023_01_09.fasta"
write.csv(UniProtFasta_info, "03_output_files/UniProtFasta_info_Mouse.csv")
For each entry, ‘Protein Mini-On’ was use to download Gene Ontology (GO) terms and KEGG ids associated with the proteins. This upload was performed the exact same day as the download of the fasta file was done to ensure that the IDs will be identical as the ones present in the fasta file used).
if(file.exists("./03_output_files/UniprotTable_Mus_musculus_proteome_UP000000589_2023_01_09.csv")){
UniProtTable<-read.csv("./03_output_files/UniprotTable_Mus_musculus_proteome_UP000000589_2023_01_09.csv")
}else{
download_UniProtTable(proteomeID = "UP000000589",reviewed = T)
write.csv(UniProtTable,("./03_output_files/UniprotTable_Mus_musculus_proteome_UP000000589_2023_01_09.csv"),row.names=FALSE)
}
‘Protein-Mini-on’ was then used to generate a table (UniProtTable) containing the list of GOs and their associated protein IDs
if(file.exists("./03_output_files/UniProtTable_GO.csv")){
UniProtTable_GO<-read.csv(file="./03_output_files/UniProtTable_GO.csv")
}else{
generate_UniProtTable_GO()
write.csv(UniProtTable_GO,file="./03_output_files/UniProtTable_GO.csv",row.names=FALSE)
}
‘Protein-Mini-on’ was used to download similar information from KEGG for the Pathways associated with each protein
if(file.exists("./03_output_files/UniProtTable_KEGG.csv")){
UniProtTable_KEGG<-read.csv(file="./03_output_files/UniProtTable_KEGG.csv")
}else{
generate_UniProtTable_KEGG()
write.csv(UniProtTable_KEGG,file="./03_output_files/UniProtTable_KEGG.csv",row.names=FALSE)
}
‘Protein-Mini-on’ was used to download similar information from REACTOME for the Pathways associated with each protein
UniProtTable$Reactome_List<-sub("R-HSA-9767675;","",UniProtTable$Reactome_List)
if(file.exists("./03_output_files/UniProtTable_REACTOME.csv")){
UniProtTable_REACTOME<-read.csv(file="./03_output_files/UniProtTable_REACTOME.csv")
}else{
generate_UniProtTable_REACTOME()
write.csv(UniProtTable_REACTOME,file="./03_output_files/UniProtTable_REACTOME.csv",row.names=FALSE)
}
The LFQ data contained in the proteinGroup file was loaded, the corresponding metadata was loaded
data<-extractMaxQuant(file = "01_source_files/proteinGroups.txt",cont.rm = T,site.rm = T,rev.rm = T)
## [1] "59 Proteins were removed (protein(s) only identified by site,contaminant(s),reverse hit(s))"
## [1] "LFQ quantification was used"
IDs<-extractMaxQuantIDs(file = "01_source_files/proteinGroups.txt",cont.rm = T,site.rm = T,rev.rm = T)
## [1] "59 Proteins were removed (protein(s) only identified by site,contaminant(s),reverse hit(s))"
metadata<-read.csv(file = "01_source_files/metadata.csv")
colnames(data)<-toupper(colnames(data))
colnames(metadata)<-toupper(colnames(metadata))
The data and metadata were placed in an romics_object, the sample names were retrieved from the metadata, the condition will be use for the coloring of the Figure and statistics
romics_proteins<-romicsCreateObject(data,metadata,main_factor = "condition")
romics_proteins<-romicsSampleNameFromFactor(romics_proteins,factor = "rename")
The missingness was evaluated for each channel/sample
romics_proteins<- romicsZeroToMissing(romics_proteins)
romicsPlotMissing(romics_proteins)
The proteins to be conserved for quantification were selected to contain at least 75% of complete values (3/4 samples) for a given condition, the overall missingness was evaluated after filtering.
romics_proteins<-romicsFilterMissing(romics_proteins,percentage_completeness = 50)
## [1] "678 rows were removed for the data"
## [1] "Based on the minimum completeness set at 50%"
## [1] "at least the following number of sample(s) containing data was required:"
## AAT Cela1 DKO WT
## 3 3 3 3
## [1] "3024/3702 features remained after filtering (81.69%)."
print(paste0(nrow(romics_proteins$data),"/", nrow(romics_proteins$original_data)," proteins remained after filtering", " (",round(nrow(romics_proteins$data)/nrow(romics_proteins$original_data)*100,2),"%)."))
## [1] "3024/3702 proteins remained after filtering (81.69%)."
romicsPlotMissing(romics_proteins)
The data was log2 transformed, the distriution boxplot were then plotted
romics_proteins<-log2transform(romics_proteins)
distribBoxplot(romics_proteins)
As the same quantity of protein was labelled for each sample, the expectation is that the distribution of the protein abundance is centered, therefore a median centering was performed prior to plot again the distribution boxplots.
romics_proteins<-medianCenterSample(romics_proteins)
distribBoxplot(romics_proteins)
Oultier detection will be performed
romicsOutlierEval(romics_proteins,pvalue_threshold = 0.000001,label = T)
## [1] "pmartR was not loaded it was loaded to execute this function"
## [1] "An object of class proData was created"
## [[1]]
##
## [[2]]
The grouping of the samples was evaluated
romicsHclust(romics_proteins)
Similarily, a PCA was performed prior imputation of the missing data
indPCAplot(romics_proteins, ncp=5,plotType = "percentage")
indPCAplot(romics_proteins, ncp=5,plotType = "individual",Xcomp=1,Ycomp =2,label = T)
indPCAplot(romics_proteins, ncp=5,plotType = "individual",Xcomp=2,Ycomp =3,label = F)
For some of the subsequent statistics imputations are required, we performed an imputation by assuming that the “non-detected” proteins were either low abundance or missing using the method developped by Tyranova et al. (PMID: 27348712). The gray distribution is the data distribution, the yellow distribution is the one for the random values used for imputation.
imputeMissingEval(romics_proteins,nb_stdev = 2,width_stdev = 0.5, bin=1)
romics_proteins<-imputeMissing(romics_proteins,nb_stdev = 2,width_stdev = 0.5)
distribHistogramGlobal(romics_proteins)
The hclust and PCA grouping were checked again after imputation
romicsHclust(romics_proteins)
indPCAplot(romics_proteins, plotType = "percentage")
indPCAplot(romics_proteins, plotType = "individual",Xcomp=1,Ycomp =2,label = F)
indPCAplot(romics_proteins, plotType = "individual",Xcomp=2,Ycomp =3,label = F)
indPCA3D(romics_proteins)
The means and stdev are calculated for each group
romics_proteins<-romicsMean(romics_proteins)
## [1] "The Statistics layer was added to your object"
## [1] "Means columns (*_mean) were added to the statistics"
romics_proteins<-romicsSd(romics_proteins)
## [1] "The standard deviation columns (*_sd) were added to the statistics"
romics_proteins<-romicsZscores(romics_proteins)
## [1] "Z_score_ columns were added to the statistics"
ANOVA are performed
romics_proteins<-romicsANOVA(romics_proteins)
## [1] "The ANOVA columns (ANOVA_p and ANOVA_padj) were added to the statistics"
A heatmap depicting the proteins passing an ANOVA p<0.05 is plotted, the clusters obtained were saved in the statistics.
romicsHeatmap(romics_proteins,variable_hclust_number = 5,ANOVA_filter = "p", p=0.05,sample_hclust = F,color_boundaries = c(-1.5,1.5))
romics_proteins<-romicsVariableHclust(romics_proteins,clusters = 5,ANOVA_filter = "p",p= 0.05,plot = F)
## [1] "The columns hclust_clusters was added to the statistics"
An enrichment analysis was performed for these four clusters generated
Enrichments<-romicsEnrichement(romics_object = romics_proteins,type = c("GO", "KEGG", "REACTOME"),cluster_filter = "hclust_clusters", enrichment_function="EASE")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 33 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 33 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 33 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 45 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 45 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 45 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 45 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 45 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 45 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 34 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 34 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 34 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 17 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 17 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 17 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
Enrichments <- Enrichments[Enrichments$pval<0.1 &Enrichments$fold_change>=1,]
datatable(Enrichments)
write.table(Enrichments,file="03_output_files/Enrichments_ANOVA_clusts.txt",sep="\t",row.names = F)
T.tests were added to the statistics
romics_proteins<-romicsTtest(romics_proteins,percentage_completeness = 50,reverse_order = T)
## [1] "T_test columns were added to the statistics"
romicsVolcano(romics_proteins,min_fold_change = 0,p_type = "p")
## [1] "'stat_type' was missing 't.test' were used by default"
pFrequencyPlot(romics_proteins)
## [1] "174 with ANOVA_p<0.05"
## [1] "4 with ANOVA_padj<0.05"
## [1] "96 with AAT_vs_Cela1_Ttest_p<0.05"
## [1] "1 with AAT_vs_Cela1_Ttest_padj<0.05"
## [1] "91 with AAT_vs_DKO_Ttest_p<0.05"
## [1] "1 with AAT_vs_DKO_Ttest_padj<0.05"
## [1] "189 with AAT_vs_WT_Ttest_p<0.05"
## [1] "4 with AAT_vs_WT_Ttest_padj<0.05"
## [1] "88 with Cela1_vs_DKO_Ttest_p<0.05"
## [1] "1 with Cela1_vs_DKO_Ttest_padj<0.05"
## [1] "158 with Cela1_vs_WT_Ttest_p<0.05"
## [1] "1 with Cela1_vs_WT_Ttest_padj<0.05"
## [1] "147 with DKO_vs_WT_Ttest_p<0.05"
## [1] "1 with DKO_vs_WT_Ttest_padj<0.05"
For the following comparison enrichment analyses were performed Cela1 vs WT AAT vs WT DKO vs WT AAT vs DKO Cela1 vs DKO AAT vs Cela1
modulated_Cela1_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "Cela1_vs_WT_Ttest_p",statCol_text = "<0.05")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 158 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 158 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 158 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
up_Cela1_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "Cela1_vs_WT_Ttest_p" ,statCol_text = "<0.05",statCol_filter2 = "log(Cela1/WT)",statCol_text2 = ">1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 5 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 5 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 5 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
down_Cela1_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "Cela1_vs_WT_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(Cela1/WT)",statCol_text2 = "<1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 153 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 153 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 153 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
modulated_AAT_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_WT_Ttest_p",statCol_text = "<0.05")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 189 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 189 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 189 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
up_AAT_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_WT_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(AAT/WT)",statCol_text2 = ">1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 9 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 9 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 9 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
down_AAT_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_WT_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(AAT/WT)",statCol_text2 = "<1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 180 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 180 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 180 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
modulated_DKO_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "DKO_vs_WT_Ttest_p",statCol_text = "<0.05")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 147 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 147 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 147 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
up_DKO_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "DKO_vs_WT_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(DKO/WT)",statCol_text2 = ">1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 17 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 17 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 17 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
down_DKO_vs_wt<- romicsEnrichement(romics_proteins,statCol_filter = "DKO_vs_WT_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(DKO/WT)",statCol_text2 = "<1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 130 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 130 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 130 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
modulated_Cela1_vs_DKO<- romicsEnrichement(romics_proteins,statCol_filter = "Cela1_vs_DKO_Ttest_p",statCol_text = "<0.05")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 88 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 88 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 88 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
up_Cela1_vs_DKO<- romicsEnrichement(romics_proteins,statCol_filter = "Cela1_vs_DKO_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(Cela1/DKO)",statCol_text2 = ">1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 7 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 7 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 7 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
down_Cela1_vs_DKO<- romicsEnrichement(romics_proteins,statCol_filter = "Cela1_vs_DKO_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(Cela1/DKO)",statCol_text2 = "<1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 81 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 81 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 81 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
modulated_AAT_vs_DKO<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_DKO_Ttest_p",statCol_text = "<0.05")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 91 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 91 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 91 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
up_AAT_vs_DKO<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_DKO_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(AAT/DKO)",statCol_text2 = ">1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 8 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 8 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 8 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
down_AAT_vs_DKO<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_DKO_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(AAT/DKO)",statCol_text2 = "<1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 83 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 83 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 83 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
modulated_AAT_vs_Cela1<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_Cela1_Ttest_p",statCol_text = "<0.05")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 96 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 96 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 96 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
up_AAT_vs_Cela1<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_Cela1_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(AAT/Cela1)",statCol_text2 = ">1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 8 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 8 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 8 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
down_AAT_vs_Cela1<- romicsEnrichement(romics_proteins,statCol_filter = "AAT_vs_Cela1_Ttest_p",statCol_text = "<0.05",statCol_filter2 = "log(AAT/Cela1)",statCol_text2 = "<1")
## [1] "Your ID list was containing more than one identifier separated with semicolons, only the first IDs were conserved"
## [1] "Your <query> contained 0 UniProt_IDs and 88 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 88 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
## [1] "Your <query> contained 0 UniProt_IDs and 88 UniProt_Accession (some might be redundant)."
## [1] "Your <universe> contained 0 UniProt_IDs and 3024 UniProt_Accession (some might be redundant)."
enrichments_ttest<-rbind(modulated_Cela1_vs_wt,up_Cela1_vs_wt,down_Cela1_vs_wt,
modulated_AAT_vs_wt,up_AAT_vs_wt,down_AAT_vs_wt,
modulated_DKO_vs_wt,up_DKO_vs_wt,down_DKO_vs_wt,
modulated_Cela1_vs_DKO,up_Cela1_vs_DKO,down_Cela1_vs_DKO,
modulated_AAT_vs_DKO,up_AAT_vs_DKO,down_AAT_vs_DKO,
modulated_AAT_vs_Cela1,up_AAT_vs_Cela1,down_AAT_vs_Cela1)
enrichments_ttest<-enrfilter(enrichments_ttest,pval_type = "pval",foldchange = 1,min_feature = 2)
datatable(enrichments_ttest)
write.csv(enrichments_ttest,file = "03_output_files/Enrichments_ttests.csv")
The data was exported for further exploration
results<-romicsExportData(romics_proteins,statistics = T,missing_data = T)
results<-merge(results,IDs,by.x = 0, by.y=1)
write.csv(results, file= "./03_output_files/Results_with_stats.csv")
Example of proteins of interest or modulated were plotted
library("ggpubr")
Figs<-romics_proteins
boxplotscatter<-function(protein_name="protein_name"){
title<-rownames(Figs$data[grepl(paste0(".*",protein_name,".*"),rownames(Figs$data)),])
title<-paste0(gsub("//.*","",title)," - ",gsub(" .*","",UniProtTable$Gene_Name[UniProtTable$Uniprot_Accession %in% protein_name]))
yposition <- max(Figs$data[grepl(paste0(".*",protein_name,".*"),rownames(Figs$data)),])
singleVariablePlot(Figs,variable =protein_name)+ggtitle(label = title)+
geom_bracket(xmin = "AAT", xmax = "WT", y.position = yposition+3.5, label =formatC(Figs$statistics[grepl(paste0(".*",protein_name,".*"),rownames(Figs$statistics)),colnames(Figs$statistics)=="AAT_vs_WT_Ttest_p"], format = "f"))+
geom_bracket(xmin = "Cela1", xmax = "WT", y.position = yposition+1.5, label =formatC(Figs$statistics[grepl(paste0(".*",protein_name,".*"),rownames(Figs$statistics)),colnames(Figs$statistics)=="Cela1_vs_WT_Ttest_p"], format = "f"))+
geom_bracket(xmin = "DKO", xmax = "WT", y.position = yposition+0.5, label =formatC(Figs$statistics[grepl(paste0(".*",protein_name,".*"),rownames(Figs$statistics)),colnames(Figs$statistics)=="DKO_vs_WT_Ttest_p"], format = "f"))+
geom_bracket(xmin = "AAT", xmax = "DKO", y.position = yposition+2.5, label =formatC(Figs$statistics[grepl(paste0(".*",protein_name,".*"),rownames(Figs$statistics)),colnames(Figs$statistics)=="AAT_vs_DKO_Ttest_p"], format = "f"))+
geom_bracket(xmin = "Cela1", xmax = "DKO", y.position = yposition+0.5, label =formatC(Figs$statistics[grepl(paste0(".*",protein_name,".*"),rownames(Figs$statistics)),colnames(Figs$statistics)=="Cela1_vs_DKO_Ttest_p"], format = "f"))+
geom_bracket(xmin = "AAT", xmax = "Cela1", y.position = yposition+0.5, label =formatC(Figs$statistics[grepl(paste0(".*",protein_name,".*"),rownames(Figs$statistics)),colnames(Figs$statistics)=="AAT_vs_Cela1_Ttest_p"], format = "f"))
}
boxplotscatter(protein_name = "Q00897")
boxplotscatter(protein_name = "P07758")
boxplotscatter(protein_name = "P22599")
boxplotscatter(protein_name = "Q920H1")
boxplotscatter(protein_name = "P50405")
boxplotscatter(protein_name = "Q06770")
boxplotscatter(protein_name = "Q9D3B1")
boxplotscatter(protein_name = "Q3UVK0")
boxplotscatter(protein_name = "Q9CQ73")
boxplotscatter(protein_name = "Q9DBJ3")
boxplotscatter(protein_name = "P98203")
boxplotscatter(protein_name = "Q505D7")
boxplotscatter(protein_name = "Q8R1S0")
boxplotscatter(protein_name = "Q6ZWY8")
boxplotscatter(protein_name = "A2AVZ9")
boxplotscatter(protein_name = "P13745")